Machine learning to automate outfit advice

Outfit advice is about being inspired by someone who understands you, and it will continue being so.

At Chicisimo, we are focused on helping people express their needs, gaining a deep understanding on how we can help them decide what to wear. We do this through our mobile app.

We are also focused on giving structure to the incoming data. Data is contained in our patented Social Fashion Graph. This graph captures how needs, outfits and people interrelate. It is a high-quality, well curated and growing fashion dataset, linked to a learning and training world: our app.

Both our mobile app and our Social Fashion Graph, are the founding patented technology assets towards our goal of automating outfit advice.

The future of fashion sounds awesome!

The way we enjoy our clothes and find new ones is going to change. The fundamentals of this change can be explained by looking at the music sector.

In the old days, we used radiocassettes to listen to music, and we could not send our taste to any capturing mechanism. “Discovery” was limited. Years later, Audioscrobbler was born and built a mechanism for us to express our taste, by tracking the songs we played. This new data allowed product builders to create new discovery experiences, giving birth to online music as we know it today.

The songs we listen to. The clothes we wear. At Chicisimo, we love how the future looks on top of this new understanding.

Digitizing offline data, and taking it online

The data necessary to provide outfit advice belongs to the offline world: what I need, what my context is, what I own in my closet, and what I wear.

There is a strong value in digitizing this data, in finding ways for people to express their needs.

Building the Social Fashion Graph.

We’ve built and patented our Social Fashion Graph to provide structure to the incoming data.

The Social Fashion Graph captures how needs, outfits and people interrelate. It is a high-quality, well curated and growing fashion dataset, linked to a learning and training world: our app.

We’ve built an ontology of the world’s what-to-wear needs. The traditional Machine Learning approach thinks of a fashion taxonomy as a list of tags describing garment characteristics. However, our app data has taught us that people’s needs go well beyond garment-related metadata, and of course these needs are expressed in very different ways.

Our ontology summarizes and gives structure to the richness of needs. Our Social Fashion Graph attaches needs to outfits and to people.

Personalizing outfit

The Social Fashion Graph contains the world’s data, but one person has a specific need at a specific time.

It is important to find the right way for people to express their specific need, and at the same time understand other more permanent needs she might have. Facilitating the input is an important area of focus for us.

Thanks for creating this app, it is helping me enjoy my clothes more and more
Feeling pretty makes me feel stronger. Chicisimo helps me getting there
I totally love helping other women with my selection of ideas

Product first

Product first. Building the right product experience is first for us.

It also allows us to learn what is the data that makes an impact and what is the technology that needs to be built, in order achieve our objetive of helping people decide what to wear.

And we love the feedback we receive, and how we are regularly featured as App of the Day by Apple in more than 60 countries in 2017, and being Android’s Best App in Spain and France 2015 and 2016.

Luckily, we are not alone

We are lucky to share a common goal with brilliant teams out there. Here is a few problems being tackled:

  • Automating outfitAmazon, Alibaba, Chicisimo
  • Image understanding and search (Most effort directed is here)Wide-Eyes, Vue.ai, ViSenze
  • Systems to match outfits and productsInstagram, Pinterest, Amazon, Chicisimo
  • Discovery of clothesAmazon, Zalando, Asos, Chicisimo

If the above makes sense to you, please

We use our own and third party cookies to offer you a better user experience. When you use our services, we understand that you accept the use we make of cookies.